Copertina

Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Los, Denis, Petushkov, Igor
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Fine-grained Task Parallelism on Simultaneous Multithreading Cores
di: Los, Denis, et al.
Pubblicazione: (2024)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
di: Pan, Xinglin, et al.
Pubblicazione: (2025)

Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization
di: Wu, Ruilong, et al.
Pubblicazione: (2025)

Astra: Efficient and Money-saving Automatic Parallel Strategies Search on Heterogeneous GPUs
di: Wang, Peiran, et al.
Pubblicazione: (2025)

On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance
di: Singh, Jaskirat, et al.
Pubblicazione: (2024)

AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
di: Luo, Xubin, et al.
Pubblicazione: (2026)

Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism
di: Zhao, Long, et al.
Pubblicazione: (2026)

Dora: QoE-Aware Hybrid Parallelism for Distributed Edge AI
di: Jin, Jianli, et al.
Pubblicazione: (2025)

Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
di: Yu, Hanfei, et al.
Pubblicazione: (2025)

Binary Bleed: Fast Distributed and Parallel Method for Automatic Model Selection
di: Barron, Ryan, et al.
Pubblicazione: (2024)

ELANA: A Simple Energy and Latency Analyzer for LLMs
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2025)

Large Language Model Partitioning for Low-Latency Inference at the Edge
di: Kafetzis, Dimitrios, et al.
Pubblicazione: (2025)

Compass: A Decentralized Scheduler for Latency-Sensitive ML Workflows
di: Yang, Yuting, et al.
Pubblicazione: (2024)

Designing Datacenter Power Delivery Hierarchies for the AI Era
di: Wilkins, Grant, et al.
Pubblicazione: (2026)

Reconstruction-Based Adaptive Scheduling Using AI Inferences in Safety-Critical Systems
di: Alshaer, Samer, et al.
Pubblicazione: (2025)

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput
di: Song, Jingwei, et al.
Pubblicazione: (2025)

Latency-Aware 2-Opt Monotonic Local Search for Distributed Constraint Optimization
di: Rachmut, Ben, et al.
Pubblicazione: (2025)

StreamServe: Adaptive Speculative Flows for Low-Latency Disaggregated LLM Serving
di: Kumar, Satyam, et al.
Pubblicazione: (2026)

PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications
di: Mell, Stephen, et al.
Pubblicazione: (2026)

Accelerated Digital Twin Learning for Edge AI: A Comparison of FPGA and Mobile GPU
di: Xu, Bin, et al.
Pubblicazione: (2025)

Keep Your Friends Close: Leveraging Affinity Groups to Accelerate AI Inference Workflows
di: Garrett, Thiago, et al.
Pubblicazione: (2023)

Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems
di: Yang, Haowei, et al.
Pubblicazione: (2025)

FreeRide: Harvesting Bubbles in Pipeline Parallelism
di: Zhang, Jiashu, et al.
Pubblicazione: (2024)

KAITIAN: A Unified Communication Framework for Enabling Efficient Collaboration Across Heterogeneous Accelerators in Embodied AI Systems
di: Lin, Jieke, et al.
Pubblicazione: (2025)

CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control
di: Buo, Antoonio, et al.
Pubblicazione: (2026)

Collaborative Split Federated Learning with Parallel Training and Aggregation
di: Papageorgiou, Yiannis, et al.
Pubblicazione: (2025)

Can Large Language Models Write Parallel Code?
di: Nichols, Daniel, et al.
Pubblicazione: (2024)

Shared Memory-Aware Latency-Sensitive Message Aggregation for Fine-Grained Communication
di: Chandrasekar, Kavitha, et al.
Pubblicazione: (2024)

iOS as Acceleration
di: Chen, Alexander K.
Pubblicazione: (2025)

TimelyFreeze: Adaptive Parameter Freezing Mechanism for Pipeline Parallelism
di: Cho, Seonghye, et al.
Pubblicazione: (2026)

Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs
di: Chen, Aodong, et al.
Pubblicazione: (2023)

TAPAS: Fast and Automatic Derivation of Tensor Parallel Strategies for Large Neural Networks
di: Shi, Ziji, et al.
Pubblicazione: (2023)

SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile
di: Zhang, Ruisi, et al.
Pubblicazione: (2024)

HPC-Coder: Modeling Parallel Programs using Large Language Models
di: Nichols, Daniel, et al.
Pubblicazione: (2023)

Para-B&B: Load-Balanced Deterministic Parallelization of Solving MIP
di: Zhang, Jinyu, et al.
Pubblicazione: (2026)

RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators
di: Tang, Xinsheng, et al.
Pubblicazione: (2026)

AdaPtis: Reducing Pipeline Bubbles with Adaptive Pipeline Parallelism on Heterogeneous Models
di: Guo, Jihu, et al.
Pubblicazione: (2025)

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
di: Fang, Jiarui, et al.
Pubblicazione: (2024)

Training Through Failure: Effects of Data Consistency in Parallel Machine Learning Training
di: Cao, Ray, et al.
Pubblicazione: (2024)

Using Sequential Runtime Distributions for the Parallel Speedup Prediction of SAT Local Search
di: Arbelaez, Alejandro, et al.
Pubblicazione: (2024)